Christian Thurau

Our work on data mining in World of Warcraft is described in a featured article in Science (the article reports on the CIG conference held in Copenhagen a few weeks ago). You can download the article from this site.

You can find more details on our work on Wow in the following papers:

• Christian Thurau, Kristian Kersting, and Christian Bauckhage. Convex Non-Negative Matrix Factorization in the Wild. ICDM 2009. [PDF]
• Christian Thurau and Christian Bauckhage. Analyzing
  the Evolution of Social Groups in World of Warcraft. CIG 2010.

We recently developed another large-scale variant of Archetypal Analysis, see the following paper for details:

• Christian Thurau, Kristian Kersting, and Christian Bauckhage.Yes We Can – Simplex Volume Maximization for Descriptive Web-Scale Matrix Factorization. CIKM 2010. [PDF]

The code (also for the large-scale archetypal analysis variant) is available in the Python Matrix Factorization Module.